Abstract | ||
---|---|---|
The lack of labeled data and the need to update the learning model are the two main challenges when performing Opinion Mining with data streams. Usual Opinion Mining approaches are not able to deal with these challenges, nor with the characteristics brought by this kind of data. Moreover, the occurrence of changes (drifts) in the concepts and/or opinions is another issue. Possible alternative solutions to these problems are: the use of Semi-supervised learning, such as Active Learning, which labels selected data rather than the entire data set; or Multiple Classifiers Systems, which combines different classifiers and are well suited to deal with drifts. In this study, we combined these two approaches, proposing the use of eight Active Learning sampling strategies as a generation method for Multiple Classifiers Systems. The Active Learning approach requires the choice of a strategy to select the instances, and each strategy results in the creation of a distinct classification model. Our method was evaluated in 14 Twitter stream data sets and the results showed that it can be better for Opinion Mining with data streams than popular ensemble generation methods present in the literature, such as Bagging and AdaBoost. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/BRACIS.2019.00029 | 2019 8th Brazilian Conference on Intelligent Systems (BRACIS) |
Keywords | Field | DocType |
Opinion Mining,Multiple Classifiers Systems,Active Learning,Ensemble generation | Data stream mining,AdaBoost,Active learning,Sentiment analysis,Computer science,Stream data,Artificial intelligence,Sampling (statistics),Labeled data,Machine learning | Conference |
ISSN | ISBN | Citations |
2643-6256 | 978-1-7281-4254-8 | 0 |
PageRank | References | Authors |
0.34 | 20 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Douglas Vitório | 1 | 4 | 2.42 |
Ellen Souza | 2 | 0 | 0.34 |
Adriano L. I. Oliveira | 3 | 364 | 36.36 |